mxnet
|
implementation of GPU host code More...
Go to the source code of this file.
Namespaces | |
mshadow | |
overloaded + operator between half_t and bf16_t | |
Functions | |
template<> | |
void | mshadow::InitTensorEngine< gpu > (int dev_id) |
template<> | |
void | mshadow::ShutdownTensorEngine< gpu > (void) |
template<> | |
void | mshadow::SetDevice< gpu > (int devid) |
template<int dim, typename DType > | |
void | mshadow::AllocSpace (Tensor< gpu, dim, DType > *obj, bool pad=MSHADOW_ALLOC_PAD) |
CPU/CPU: allocate space for CTensor, according to the shape in the obj this function is responsible to set the stride_ in each obj.shape. More... | |
template<int dim, typename DType > | |
void | mshadow::FreeSpace (Tensor< gpu, dim, DType > *obj) |
CPU/GPU: free the space of tensor, will set obj.dptr to NULL. More... | |
template<typename A , typename B , int dim, typename DType > | |
void | mshadow::Copy (Tensor< A, dim, DType > _dst, Tensor< B, dim, DType > _src, cudaMemcpyKind kind, Stream< gpu > *stream) |
template<int dim, typename DType > | |
void | mshadow::Copy (Tensor< cpu, dim, DType > dst, const Tensor< gpu, dim, DType > &src, Stream< gpu > *stream=NULL) |
copy data from one tensor to another, with same shape More... | |
template<int dim, typename DType > | |
void | mshadow::Copy (Tensor< gpu, dim, DType > dst, const Tensor< gpu, dim, DType > &src, Stream< gpu > *stream=NULL) |
copy data from one tensor to another, with same shape More... | |
template<int dim, typename DType > | |
void | mshadow::Copy (Tensor< gpu, dim, DType > dst, const Tensor< cpu, dim, DType > &src, Stream< gpu > *stream=NULL) |
copy data from one tensor to another, with same shape More... | |
implementation of GPU host code